feat: stubs for desbordante 2.1.0

.github/workflows/lint.yaml

@@ -0,0 +1,21 @@
+name: Lint
+on:
+  pull_request:
+  push:
+jobs:
+  run-linters:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+
+      - name: Install deps
+        run: python3 -m pip install poetry==1.8.2 && make init
+
+      - name: Run all linters and formatters
+        run: make lint

.pre-commit-config.yaml

@@ -0,0 +1,33 @@
+fail_fast: true
+default_language_version:
+  python: python3.12
+
+ci:
+  autoupdate_commit_msg: "chore: update pre-commit hooks"
+  autofix_commit_msg: "style: pre-commit fixes"
+  skip: [make-format, make-lint]
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-symlinks
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+      - id: requirements-txt-fixer
+      - id: trailing-whitespace
+
+  - repo: local
+    hooks:
+      - id: make-format
+        name: make-format
+        entry: make format
+        language: system
+
+      - id: make-lint
+        name: make-lint
+        entry: make lint
+        language: system

Makefile

@@ -0,0 +1,30 @@
+.PHONY: init lint format stubs
+
+## Install dependencies
+init:
+	poetry install
+	poetry run pre-commit install
+
+## Run all formatters and linters in project
+lint:
+	poetry run ruff check desbordante-stubs \
+	& poetry run ruff format --check desbordante-stubs \
+	& poetry run black --check desbordante-stubs
+
+## Reformat code
+format:
+	poetry run ruff format desbordante-stubs & poetry run ruff check --fix & poetry run black desbordante-stubs
+
+## Generate stubs
+stubs:
+	pybind11-stubgen desbordante
+	@if [ -d "desbordante-stubs" ]; then rm -rf desbordante-stubs; fi
+	@if [ -d "stubs/desbordante" ]; then mv stubs/desbordante desbordante-stubs; fi
+	rm -rf stubs
+	make format
+
+
+.DEFAULT_GOAL := help
+# See <https://gist.github.com/klmr/575726c7e05d8780505a> for explanation.
+help:
+	@echo "$$(tput setaf 2)Available rules:$$(tput sgr0)";sed -ne"/^## /{h;s/.*//;:d" -e"H;n;s/^## /---/;td" -e"s/:.*//;G;s/\\n## /===/;s/\\n//g;p;}" ${MAKEFILE_LIST}|awk -F === -v n=$$(tput cols) -v i=4 -v a="$$(tput setaf 6)" -v z="$$(tput sgr0)" '{printf"- %s%s%s\n",a,$$1,z;m=split($$2,w,"---");l=n-i;for(j=1;j<=m;j++){l-=length(w[j])+1;if(l<= 0){l=n-i-length(w[j])-1;}printf"%*s%s\n",-i," ",w[j];}}'

desbordante-stubs/__init__.pyi

@@ -1,15 +1,24 @@
 """
 A high-performance data profiling library oriented towards exploratory data analysis
 """
+
 from __future__ import annotations
 import typing
 from . import ac
 from . import afd
+from . import aind
 from . import ar
+from . import cfd
 from . import data_types
+from . import dd
+from . import dynamic_fd_verification
 from . import fd
 from . import fd_verification
+from . import gfd_verification
+from . import ind
 from . import mfd_verification
+from . import od
+from . import pfd
 from . import statistics
 from . import ucc
 from . import ucc_verification
@@ -20,11 +29,21 @@ __all__ = [
     "ac",
     "afd",
     "afd_verification",
+    "aind",
     "ar",
+    "aucc_verification",
+    "cfd",
     "data_types",
+    "dd",
+    "dynamic_fd_verification",
     "fd",
     "fd_verification",
+    "gfd_verification",
+    "ind",
     "mfd_verification",
+    "od",
+    "od_module",
+    "pfd",
     "statistics",
     "ucc",
     "ucc_verification",
@@ -35,10 +54,12 @@ class Algorithm:
         """
         Process data.
         """
+
     def get_description(self, option_name: str) -> str:
         """
         Get description of an option.
         """
+
     def get_needed_options(self) -> set[str]:
         """
         Get names of options the algorithm requires to be set at the moment.
@@ -47,22 +68,27 @@ class Algorithm:
         algorithms' options using keyword arguments of the load_data and execute
         methods.
         """
+
     def get_option_type(self, option_name: str) -> tuple:
         """
         Get info about the option's type.
         """
+
     def get_opts(self) -> dict[str, typing.Any]:
         """
         Get option values represented as the closest Python type
         """
+
     def get_possible_options(self) -> set[str]:
         """
         Get names of options the algorithm may request.
         """
+
     def load_data(self, **kwargs) -> None:
         """
         Load data for execution
         """
+
     def set_option(self, option_name: str, option_value: typing.Any = None) -> None:
         """
         Set option value. Passing None means setting the default value.
@@ -76,3 +102,5 @@ class ConfigurationError(ValueError):
     pass
 
 afd_verification = fd_verification
+aucc_verification = ucc_verification
+od_module = od

desbordante-stubs/ac/algorithms.pyi

@@ -16,6 +16,7 @@ class AcAlgorithm(desbordante.Algorithm):
     iterations_limit: limit for iterations of sampling
     ac_seed: seed, needed for choosing a data sample
     """
+
     def __init__(self) -> None: ...
     def get_ac_exceptions(self) -> list[desbordante.ac.ACException]: ...
     def get_ac_ranges(self) -> list[desbordante.ac.ACRanges]: ...

desbordante-stubs/aind/__init__.pyi

@@ -0,0 +1,4 @@
+from __future__ import annotations
+from . import algorithms
+
+__all__ = ["algorithms"]

desbordante-stubs/aind/algorithms.pyi

@@ -0,0 +1,6 @@
+from __future__ import annotations
+from desbordante.ind.algorithms import Mind
+from desbordante.ind.algorithms import Spider
+from desbordante.ind.algorithms import Spider as Default
+
+__all__ = ["Default", "Mind", "Spider"]

desbordante-stubs/ar/__init__.pyi

@@ -2,16 +2,26 @@ from __future__ import annotations
 import desbordante
 from . import algorithms
 
-__all__ = ["ArAlgorithm", "AssociativeRule", "algorithms"]
+__all__ = ["ARStrings", "ArAlgorithm", "ArIDs", "algorithms"]
 
-class ArAlgorithm(desbordante.Algorithm):
-    def get_ars(self) -> list[AssociativeRule]: ...
-
-class AssociativeRule:
+class ARStrings:
     def __str__(self) -> str: ...
     @property
     def confidence(self) -> float: ...
     @property
     def left(self) -> list[str]: ...
     @property
     def right(self) -> list[str]: ...
+
+class ArAlgorithm(desbordante.Algorithm):
+    def get_ar_ids(self) -> list[ArIDs]: ...
+    def get_ars(self) -> list[ARStrings]: ...
+    def get_itemnames(self) -> list[str]: ...
+
+class ArIDs:
+    @property
+    def confidence(self) -> float: ...
+    @property
+    def left(self) -> list[int]: ...
+    @property
+    def right(self) -> list[int]: ...

desbordante-stubs/ar/algorithms.pyi

@@ -15,6 +15,7 @@ class Apriori(desbordante.ar.ArAlgorithm):
     minsup: minimum support value (between 0 and 1)
     tid_column_index: index of the column where a TID is stored
     """
+
     def __init__(self) -> None: ...
 
 Default = Apriori

desbordante-stubs/cfd/__init__.pyi

@@ -0,0 +1,21 @@
+from __future__ import annotations
+import desbordante
+from . import algorithms
+
+__all__ = ["CFD", "CfdAlgorithm", "Item", "algorithms"]
+
+class CFD:
+    def __str__(self) -> str: ...
+    @property
+    def lhs_items(self) -> list[Item]: ...
+    @property
+    def rhs_item(self) -> Item: ...
+
+class CfdAlgorithm(desbordante.Algorithm):
+    def get_cfds(self) -> list[CFD]: ...
+
+class Item:
+    @property
+    def attribute(self) -> int: ...
+    @property
+    def value(self) -> str | None: ...

desbordante-stubs/cfd/algorithms.pyi

@@ -0,0 +1,21 @@
+from __future__ import annotations
+import desbordante.cfd
+
+__all__ = ["Default", "FDFirst"]
+
+class FDFirst(desbordante.cfd.CfdAlgorithm):
+    """
+    Options:
+    table: table processed by the algorithm
+    columns_number: Number of columns in the part of the dataset if you want to use algo not on the full dataset, but on its part
+    cfd_minsup: minimum support value (integer number between 1 and number of tuples in dataset)
+    cfd_minconf: cfd minimum confidence value (between 0 and 1)
+    tuples_number: Number of tuples in the part of the dataset if you want to use algo not on the full dataset, but on its part
+    cfd_max_lhs: cfd max considered LHS size
+    cfd_substrategy: CFD lattice traversal strategy to use
+    [dfs|bfs]
+    """
+
+    def __init__(self) -> None: ...
+
+Default = FDFirst

desbordante-stubs/data_types.pyi

@@ -1,13 +1,21 @@
 """
 
-        Contains the types of data supported by Desbordante.
+Contains the types of data supported by Desbordante.
+
+Currently only used as tags for Algorithm.get_option_type
 
-        Currently only used as tags for Algorithm.get_option_type
-    
 """
+
 from __future__ import annotations
 
-__all__ = ["Table"]
+__all__ = ["ColumnCombination", "Table"]
+
+class ColumnCombination:
+    def __str__(self) -> str: ...
+    @property
+    def column_indices(self) -> list[int]: ...
+    @property
+    def table_index(self) -> int: ...
 
 class Table:
     pass

desbordante-stubs/dd/__init__.pyi

@@ -0,0 +1,8 @@
+from __future__ import annotations
+from . import algorithms
+
+__all__ = ["DD", "algorithms"]
+
+class DD:
+    def __repr__(self) -> str: ...
+    def __str__(self) -> str: ...

desbordante-stubs/dd/algorithms.pyi

@@ -0,0 +1,19 @@
+from __future__ import annotations
+import desbordante
+import desbordante.dd
+
+__all__ = ["Default", "Split"]
+
+class Split(desbordante.Algorithm):
+    """
+    Options:
+    table: table processed by the algorithm
+    difference_table: CSV table containing difference limits for each column
+    num_rows: Use only first N rows of the table
+    num_columns: Use only first N columns of the table
+    """
+
+    def __init__(self) -> None: ...
+    def get_dds(self) -> list[desbordante.dd.DD]: ...
+
+Default = Split

desbordante-stubs/dynamic_fd_verification/__init__.pyi

@@ -0,0 +1,4 @@
+from __future__ import annotations
+from . import algorithms
+
+__all__ = ["algorithms"]

desbordante-stubs/dynamic_fd_verification/algorithms.pyi

@@ -0,0 +1,24 @@
+from __future__ import annotations
+import desbordante
+import desbordante.fd_verification
+
+__all__ = ["Default", "DynamicFDVerifier"]
+
+class DynamicFDVerifier(desbordante.Algorithm):
+    """
+    Options:
+    table: table processed by the algorithm
+    insert: Rows to be inserted into the table using the insert operation
+    delete: Rows to be deleted from the table using the delete operation
+    update: Rows to be replaced in the table using the update operation
+    lhs_indices: LHS column indices
+    rhs_indices: RHS column indices
+    """
+
+    def __init__(self) -> None: ...
+    def fd_holds(self) -> bool: ...
+    def get_error(self) -> float: ...
+    def get_highlights(self) -> list[desbordante.fd_verification.Highlight]: ...
+    def get_num_error_clusters(self) -> int: ...
+
+Default = DynamicFDVerifier